Detailed Action
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-9 are pending for examination. Claim 1 is independent.
Response to Restriction
Applicant had elected Group 1 including claims 1-9.
Specification
The disclosure is objected to because of the following informalities: Para 0047 of the specification states "LIF neuron model" without defining what "LIF" stands for.
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-9 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1
According to the first part of the analysis, in the instant case the claims fall within one of the four statutory categories (i.e., process, machine, manufacture, or composition of matter).
Regarding Claim 1:
2A Prong 1:
an accumulation step: performing weighted summation based on the at least one path of input spike train to obtain a membrane potential; (This step for performing a weighted summation is practically performable in the human mind and is understood to be a recitation of a mental process (i.e., evaluation) or mathematical calculation.) and
an activation step: when the membrane potential exceeds a threshold value, determining an amplitude of a spike fired by the at least one neuron based on a ratio of the membrane potential to the threshold value. (This step is practically performable in the human mind and is understood to be a recitation of a mental process (i.e., evaluation) or mathematical calculation.)
2A Prong 2: This judicial exception is not integrated into a practical application.
Additional elements:
A signal processing method for neurons in a spiking neural network, wherein the spiking neural network comprises a plurality of layers, each of the layers comprises a plurality of neurons, and the signal processing method comprises following steps: (This step is adding the words “apply it” (or an equivalent) with the judicial exception, or merely applying a neural network as a tool to perform the abstract idea (i.e., predicting) - see MPEP 2106.05(f).)
a receiving step: at least one neuron configured to receive at least one path of input spike train; (This step is directed to transmitting or receiving information, which is understood to be insignificant extra-solution activity and data gathering. See MPEP 2106.05(g).)
The additional elements as disclosed above alone or in combination do not integrate the judicial exception into practical application as they are insignificant extra solution activity in combination of generic computer functions that are implemented to perform the disclosed abstract idea above.
2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
A signal processing method for neurons in a spiking neural network, wherein the spiking neural network comprises a plurality of layers, each of the layers comprises a plurality of neurons, and the signal processing method comprises following steps: (This step is adding the words “apply it” (or an equivalent) with the judicial exception, or merely applying a neural network as a tool to perform the abstract idea (i.e., predicting) - see MPEP 2106.05(f).)
a receiving step: at least one neuron configured to receive at least one path of input spike train; (This step is directed to transmitting or receiving information, which is understood to be insignificant extra-solution activity and is well understood, routine and conventional activity of transmitting and receiving data as identified by the court (MPEP2106.05(d)(ll)(i))))
The additional elements as disclosed above in combination of the abstract idea
are not sufficient to amount to significantly more than the judicial exception as they are
well, understood, routine and conventional activity as disclosed in combination
of generic computer functions that are implemented to perform the disclosed abstract idea above.
Regarding Claim 2
2A Prong 1:
wherein determining the amplitude of the spike fired by the at least one neuron based on the ratio of the membrane potential to the threshold value comprises: wherein in a single-simulation time step, an amplitude of an fired spike is related to the ratio of the membrane potential to the threshold value. (This step is practically performable in the human mind and is understood to be a recitation of a mental process (i.e., evaluation).)
2A Prong 2 & 2B: The claim does not recite any additional elements.
Regarding Claim 3
2A Prong 1:
wherein determining the amplitude of the spike fired by the at least one neuron based on the ratio of the membrane potential to the threshold value comprises: wherein in a single-simulation time step, the ratio of an amplitude of an fired spike to a unit spike amplitude is equal to a rounded down value of the ratio of the membrane potential to the threshold value. (This step is practically performable in the human mind and is understood to be a recitation of a mental process (i.e., evaluation).)
2A Prong 2 & 2B: The claim does not recite any additional elements.
Regarding Claim 4
2A Prong 1:
wherein performing weighted summation based on the at least one path of input spike train to obtain the membrane potential comprises: performing weighted summation based on a post synaptic potential kernel convolved with each path of input spike train to obtain the membrane potential. (This step is practically performable in the human mind and is understood to be a recitation of a mental process (i.e., evaluation) or mathematical calculation.)
2A Prong 2 & 2B: The claim does not recite any additional elements.
Regarding Claim 5
2A Prong 1:
wherein performing weighted summation based on the at least one path of input spike train to obtain the membrane potential comprises: performing weighted summation based on the post synaptic potential kernel convolved with each path of input spike train and performing convolution of a refractory kernel with an output spike train of the neuron to obtain the membrane potential. (This step is practically performable in the human mind and is understood to be a recitation of a mental process (i.e., evaluation) or mathematical calculation.)
2A Prong 2 & 2B: The claim does not recite any additional elements.
Regarding Claim 6
2A Prong 1:
The signal processing method for neurons in the spiking neural network as claimed in claim 4, wherein:
v
t
=
∑
j
w
j
∈
*
S
j
(
t
)
wherein v(t) is the membrane potential of the neuron, wj is a jth synaptic weight, ϵ(t) is the post synaptic potential kernel, sj (t) is a jth input spike train, ‘*’ is a convolution operation, and t is time. (This step is practically performable in the human mind and is understood to be a recitation of mathematical calculation.)
2A Prong 2 & 2B: The claim does not recite any additional elements.
Regarding Claim 7
2A Prong 1:
The signal processing method for neurons in the spiking neural network as claimed in claim 5, wherein:
v
t
=
η
*
s
'
t
+
∑
j
w
j
(
ϵ
*
s
j
)
(
t
)
wherein v(t) is the membrane potential of the neuron, η(t) is the refractory kernel, s'(t) is the output spike train of the neuron, wj is a jth synaptic weight, ϵ(t) is the post synaptic potential kernel, sj (t) is a jth input spike train, ‘*’ is a convolution operation, and t is time. (This step is practically performable in the human mind and is understood to be a recitation of mathematical calculation.)
2A Prong 2 & 2B: The claim does not recite any additional elements.
Regarding Claim 8
2A Prong 1:
The signal processing method for neurons in the spiking neural network as claimed in claim 6, wherein the post synaptic potential kernel is
ϵ
t
=
ϵ
s
*
ϵ
v
(
t
)
, a synaptic dynamic function is
ϵ
s
t
=
e
-
t
/
τ
s
, a membrane dynamic function is
ϵ
v
t
=
e
-
t
/
τ
v
,
τ
s
is a synaptic time constant,
τ
v
is a membrane time constant, and t is time. (This step is practically performable in the human mind and is understood to be a recitation of mathematical calculation.)
2A Prong 2 & 2B: The claim does not recite any additional elements.
Regarding Claim 9
2A Prong 1:
The signal processing method for neurons in the spiking neural network as claimed in claim 7, wherein the post synaptic potential kernel is
ϵ
t
=
ϵ
s
*
ϵ
v
(
t
)
, a synaptic dynamic function is
ϵ
s
t
=
e
-
t
/
τ
s
, a membrane dynamic function is
ϵ
v
t
=
e
-
t
/
τ
v
,
τ
s
is a synaptic time constant,
τ
v
is a membrane time constant, and t is time; the refractory kernel is
η
t
=
-
θ
e
-
t
/
τ
v
, θ is the threshold value, and when v(t) ≥ θ, s’(t) = [v(t)/θ], or otherwise s’(t) = 0. (This step is practically performable in the human mind and is understood to be a recitation of mathematical calculation.)
2A Prong 2 & 2B: The claim does not recite any additional elements.
Allowable Subject Matter over prior art
Regarding Claim 9
Shrestha et al. ("SLAYER: Spike Layer Error Reassignment in Time") teaches a spiking neural network performing weighted summation based on a input spike train to obtain a membrane potential.
Xu et al. ("Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators Using Time Compression Supporting Multiple Spike Codes") teaches producing an output spike train in weighted form, where each output spike reflects the amplitude of the membrane potential as a multiple of the firing threshold.
None of these references taken alone or in combination with the prior art of
record disclose the same steps for calculating a refractory kernel when v(t) ≥ θ, s’(t) = [v(t)/θ], or otherwise s’(t) = 0 as described in the claim, in combination with the remaining elements and features of the claimed invention. It is for these reasons that the applicants’ invention defines over the prior art of record.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shrestha et al. ("SLAYER: Spike Layer Error Reassignment in Time", hereinafter "Shrestha") in view of Xu et al. ("Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators Using Time Compression Supporting Multiple Spike Codes", hereinafter "Xu").
Regarding Claim 1
Shrestha discloses: A signal processing method for neurons in a spiking neural network, wherein the spiking neural network comprises a plurality of layers, each of the layers comprises a plurality of neurons ([Abstract, Introduction, and Section 2] describe processing for a spiking neural network.), and the signal processing method comprises following steps:
a receiving step: at least one neuron configured to receive at least one path of input spike train; ([Section 2] describes an input spike train.)
an accumulation step: performing weighted summation based on the at least one path of input spike train to obtain a membrane potential ([Section 2 and equation 1] describes a weighted summation based on the input spike to obtain a membrane potential.); and
an activation step: when the membrane potential exceeds a threshold value ([Section 2] describes an output spike is generated whenever u(t) reaches a predefined threshold.),
Shrestha does not explicitly disclose: determining an amplitude of a spike fired by the at least one neuron based on a ratio of the membrane potential to the threshold value.
However, Xu discloses in the same field of endeavor: an activation step: when the membrane potential exceeds a threshold value ([Section 2.2] describes once the membrane potential u(t)reaches the firing threshold uth, an output spike is generated.), determining an amplitude of a spike fired by the at least one neuron based on a ratio of the membrane potential to the threshold value ([Page 15 right col first para] states “we proposed a new family of input-output-weighted (IOW) spiking neural models which take the input spike trains in the weighted form and produce the output spike train in the same weighted form, where the multibit weight value of each output spike reflects the amplitude of the membrane potential as a multiple of the firing threshold.” [Section 2 and Figures 1-5] also discloses the limitation.)
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of Boosting throughput disclosed by Xu into the Spiking Neural Network disclosed by Shrestha to perform the activation step. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of Boosting throughput disclosed by Xu as all the references are in the field of spinking neural networks. A person of ordinary skill of the art would have been motivated to perform the combination for being able to boost throughput and provide multiple spike codes for a spinking neural network accelerator.
Regarding Claim 2
Shrestha in view of Xu disclose: The signal processing method for neurons in the spiking neural network as claimed in claim 1, wherein determining the amplitude of the spike fired by the at least one neuron based on the ratio of the membrane potential to the threshold value comprises: wherein in a single-simulation time step, an amplitude of an fired spike is related to the ratio of the membrane potential to the threshold value. ([Page 15 right col first para], Xu describes input-output-weighted (IOW) spiking neural models which take input spike trains in the weighted form and produce the output spike train in the same weighted form, where the multibit weight value of each output spike reflects the amplitude of the membrane potential as a multiple of the firing threshold. [Section 2 and Figures 1-5] also discloses the limitation.)
Regarding Claim 3
Shrestha in view of Xu disclose: The signal processing method for neurons in the spiking neural network as claimed in claim 1, wherein determining the amplitude of the spike fired by the at least one neuron based on the ratio of the membrane potential to the threshold value comprises: wherein in a single-simulation time step, the ratio of an amplitude of an fired spike to a unit spike amplitude is equal to a rounded down value of the ratio of the membrane potential to the threshold value. ([Page 15 right col first para], Xu describes input-output-weighted (IOW) spiking neural models which take input spike trains in the weighted form and produce the output spike train in the same weighted form, where the multibit weight value of each output spike reflects the amplitude of the membrane potential as a multiple of the firing threshold. [Section 2 and Figures 1-5] also discloses the limitation.)
Regarding Claim 4
Shrestha in view of Xu disclose: The signal processing method for neurons in the spiking neural network as claimed in claim 1, wherein performing weighted summation based on the at least one path of input spike train to obtain the membrane potential comprises: performing weighted summation based on a post synaptic potential kernel convolved with each path of input spike train to obtain the membrane potential. ([Sections 2-3 and equation 1], Shrestha describes the weighted summation.)
Regarding Claim 5
Shrestha in view of Xu disclose: The signal processing method for neurons in the spiking neural network as claimed in claim 4, wherein performing weighted summation based on the at least one path of input spike train to obtain the membrane potential comprises: performing weighted summation based on the post synaptic potential kernel convolved with each path of input spike train and performing convolution of a refractory kernel with an output spike train of the neuron to obtain the membrane potential. ([Sections 2-3 and equation 1], Shrestha Section 2.1 describes the weighted summation with refractory response and refractory kernel.)
Regarding Claim 6
Shrestha in view of Xu disclose: The signal processing method for neurons in the spiking neural network as claimed in claim 4, wherein:
v
t
=
∑
j
w
j
∈
*
S
j
(
t
)
wherein v(t) is the membrane potential of the neuron, wj is a jth synaptic weight, ϵ(t) is the post synaptic potential kernel, sj (t) is a jth input spike train, ‘*’ is a convolution operation, and t is time. ([Section 2.1 and equation 1], Shrestha discloses the formula. Also rest of Sections 2-3.)
Regarding Claim 7
Shrestha in view of Xu disclose: The signal processing method for neurons in the spiking neural network as claimed in claim 5, wherein:
v
t
=
η
*
s
'
t
+
∑
j
w
j
(
ϵ
*
s
j
)
(
t
)
wherein v(t) is the membrane potential of the neuron, η(t) is the refractory kernel, s'(t) is the output spike train of the neuron, wj is a jth synaptic weight, ϵ(t) is the post synaptic potential kernel, sj (t) is a jth input spike train, ‘*’ is a convolution operation, and t is time. ([Section 2.1 and equation 1], Shrestha discloses the formula. Also rest of Sections 2-3.)
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shrestha in view of Xu and Gerstner ("A Framework for Spiking Neuron Models The Spike Response Model", hereinafter "Gerstner").
Regarding Claim 8
Shrestha in view of Xu disclose: The signal processing method for neurons in the spiking neural network as claimed in claim 6,
Shrestha in view of Xu does not explicitly disclose: wherein the post synaptic potential kernel is
ϵ
t
=
ϵ
s
*
ϵ
v
(
t
)
, a synaptic dynamic function is
ϵ
s
t
=
e
-
t
/
τ
s
, a membrane dynamic function is
ϵ
v
t
=
e
-
t
/
τ
v
,
τ
s
is a synaptic time constant,
τ
v
is a membrane time constant, and t is time.
However, Gerstner discloses in the same field of endeavor: wherein the post synaptic potential kernel is
ϵ
t
=
ϵ
s
*
ϵ
v
(
t
)
, a synaptic dynamic function is
ϵ
s
t
=
e
-
t
/
τ
s
, a membrane dynamic function is
ϵ
v
t
=
e
-
t
/
τ
v
,
τ
s
is a synaptic time constant,
τ
v
is a membrane time constant, and t is time. ([section 4.4.3. Relation between the two integration methods and equations 50, and 72-73] also see section 4.3)
It would have been obvious to a person of ordinary skill in art before the effective filling date of the invention to implement the function of spike response model disclosed by Gerstner into the method of Shrestha in view of Xu to disclose the post synaptic potential kernel. The modification would have been obvious because one of the ordinary skills of the art would be motivated to utilize the feature of spike response model disclosed by Gerstner as all the references are in the field of spiking models. A person of ordinary skill of the art would have been motivated to perform the combination for being able to provide synaptic kernel for a spike response model.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. George (US 20190244079 A1) describes synchronized symmetry-identifying spiking artificial neural network. Eyole (US 20230087612 A1) describes a convolution spiking neural network.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TEWODROS E MENGISTU whose telephone number is (571)270-7714. The examiner can normally be reached Mon-Fri 9:30-5:30.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, ABDULLAH KAWSAR can be reached at (571)270-3169. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/TEWODROS E MENGISTU/Examiner, Art Unit 2127
Prosecution Insights